Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential outcomes or possibilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Biscuits
    -0.56
    XtraEditors
    -0.56
    nastics
    -0.52
    脚注の使い方
    -0.52
     biscuits
    -0.51
    basicConfig
    -0.49
    hdashline
    -0.47
    нями
    -0.46
     UCS
    -0.46
     Потому
    -0.46
    POSITIVE LOGITS
     candidates
    0.85
     future
    0.84
     propOrder
    0.76
     Potential
    0.76
    FUTURE
    0.75
    Potential
    0.74
     candidate
    0.74
    future
    0.73
     potential
    0.73
     candidat
    0.72
    Act Density 0.163%

    No Known Activations